Table 8 Results using two CD codebooks and one CI codebook, for context match scenario for CD-2 under babble noise
From: Robust Bayesian estimation for context-based speech enhancement
|  | ΔPESQ | ΔSSNR (in dB) | ||||
|---|---|---|---|---|---|---|
Input SNR | 0 dB | 5 dB | 10 dB | 0 dB | 5 dB | 10 dB |
CBSE with CD-1 | 0.11±0.13 | 0.09±0.09 | 0.06±0.12 | 4.15±1.02 | 3.25±1.18 | 1.55±1.44 |
CBSE with CD-2 | 0.24±0.12 | 0.21±0.13 | 0.21±0.12 | 5.22±1.07 | 4.64±1.17 | 3.02±1.32 |
CBSE with CI | 0.18±0.11 | 0.16±0.10 | 0.17±0.12 | 4.77±0.91 | 4.24±1.02 | 2.61±1.29 |
Proposed | 0.24±0.12 | 0.22±0.11 | 0.21±0.11 | 5.08±1.12 | 4.51±1.20 | 2.93±1.39 |
Reference | 0.08±0.09 | 0.10±0.07 | 0.08±0.05 | 2.59±0.49 | 3.06±0.51 | 2.71±0.52 |